AI Model Reviewer

Claude Opus 5.5 in a raw API call

raw API baseline

← Open in the gallerySame prompt, all models

Zoom, inline player and more ways to view
Poster frame of Claude Opus 5.5's page
Open the original page

The model's own page, run in a sandboxed frame only when you ask (a page that needs its own origin opens in a new tab on a separate demo site). Phones get a full-screen player capped at 1.5x pixel density (2x on larger screens) so it stays smooth; the original page runs uncapped. It starts in its auto-tour (T switches to play mode on a keyboard).

OKCinematic fjord boat scene (Three.js)low effortRaw baseline1 fix turn

Wall time 8m 59sCost $1.35 estimated

the run's capture video
Capture video. the reviewer's deterministic capture of the fixed build, with title/end cards and a music bed added in editing.

Review

After one round of the reviewer's written feedback plus four of its own frames, the scene gains layered mountains with forests, sky and atmospheric depth, a warm sunset, a starry night with a moon, and the lighthouse beam sweeping during the tour.

The full review

After one round of the reviewer's written feedback plus four of its own frames, the scene gains layered mountains with forests, sky and atmospheric depth, a warm sunset, a starry night with a moon, and the lighthouse beam sweeping during the tour. The boat and characters are still toy-like and the water is plain. Not a one-shot: it needed a human-written critique.

Verdict by site build agent (draft written from the run records and the render; not reviewed yet).

OK. Two calls: the raw one-shot above, then one fix turn with the reviewer's written feedback and a sheet of four frames from the first build. Both ended with stop_reason end_turn. Numbers are the two calls combined.

Bugs

  • Boat and characters are still basic, toy-like primitives
  • Water is a plain shaded surface; reflections only read at sunset
  • No clear snow caps on the mountains

Scores

AI judge

Not scored

No rubric for this prompt

Visitor votes and reviewer grades are not available yet.

AI judge
AI judge: the test runner (model claude-opus-5-5), scoring by visual review of the 1600 px render against the pre-registered rubric. No AI-judge score exists for this result: there is no rubric for this prompt, so no score is shown and none is made up.
Visitors
Public voting with a blind reveal is coming: you score the output first, then see the other scores.
Reviewer
The reviewer's own grade appears here once it is added.

Scores compare results for the same prompt only. AI-judge boards rank runs within one prompt, equal totals sharing a rank; scores from different prompts are never averaged.

Downloads

Files actually published for this run. Original output, site-made previews and post-run conversions are labelled separately.

The exact prompt

raw API call, 3,370 characters. Every result for this prompt

Build a playable, cinematic single-page Three.js experience: a small boat drifting through a Norwegian-style fjord / coastal mountain landscape.

Requirements:
- ONE self-contained index.html file (HTML + CSS + JS inline). No external assets of any kind (no textures, models, fonts, audio files) EXCEPT Three.js itself, loaded via an import map from this exact pinned CDN:
  "three": "https://cdn.jsdelivr.net/npm/three@0.160.0/build/three.module.js",
  "three/addons/": "https://cdn.jsdelivr.net/npm/three@0.160.0/examples/jsm/"
  All textures (water normals, rock, snow, bark, clouds, etc.) must be generated procedurally in code (canvas / DataTexture / shaders).
- Scene content: steep procedural fjord walls and mountains with snow caps, rock and grass coloring by height/slope; procedural conifer forests (instanced); a water surface with animated waves and sky/landscape reflections; a lighthouse on a rocky point with a rotating beam that matters at night; a small wooden boat with 2 simple stylized 3D characters on it (one rowing/steering, one looking around, with small idle animations); distant islands; birds or other small life if cheap.
- Dynamic weather cycling clear -> fog -> rain -> storm -> clearing, with smooth transitions: fog density, cloud cover, rain particles, lightning flashes + wind and bigger waves in the storm.
- A full day/night cycle: sunrise, day, golden hour, sunset, night with stars and moon, lit lighthouse and boat lantern. Sky color, sun/moon lights, and fog color must track time of day.
- Controls: keyboard (WASD/arrows to steer and throttle the boat, C to switch camera, T toggles auto-tour, 1-5 to force weather, N to jump time) and touch (on-screen joystick/buttons on phones). Camera follows the boat in play mode.
- An "auto-tour" cinematic camera mode: slow, smooth, film-like camera moves (orbits, low water-level glides, high establishing shots, close-ups of the characters) while the boat drifts along a path through the fjord and the weather and time of day progress.
- Minimal, elegant UI: small title "Fjordlys" (or a better name of your choice), a tiny hint line for controls, fading out in tour mode.
- Must run smoothly on desktop and phone browsers: keep geometry/particle counts moderate, cap devicePixelRatio at 2, handle resize/orientation.
- IMPORTANT for automated video capture, support these URL parameters:
  ?tour=1        start directly in auto-tour mode
  ?capture=1     hide ALL UI overlays (title, hints, touch controls)
  ?cycle=40      when present, compress one complete showcase into that many seconds: the time of day goes from morning through golden hour, sunset and night, and the weather passes clear -> fog -> rain -> storm -> clearing within that span (so a 40-second recording shows everything). Without it, use a relaxed pace suited to live play.
  Drive all animation from the requestAnimationFrame timestamp / performance.now() (not from wall-clock-independent accumulators that ignore time), so that overriding those functions steps the scene deterministically. Set window.__sceneReady = true once the first frame has rendered.
- No console errors or warnings in a current Chrome. Use modern Three.js r160 APIs only (no deprecated/removed ones).

Output ONLY the complete index.html, starting with <!DOCTYPE html> and ending with </html>, with no explanation and no markdown fences.

How it was made

Wall time 8m 59s

Step by step

The prompt, every agent turn and tool call (tool name and a one-line summary; inputs and outputs are not shown), then the final message. The full transcript is published as text (under 2 MB, secrets redacted).

Show all 9 steps

Loading the timeline…

Download the full transcript text record, 67 KB. Scrubbed: anything that looks like a key, token, e-mail address or phone number is replaced, and account details and the test machine's file paths are removed.

Cost breakdown

Headline cost $1.35, estimated from the token counts at list price.

Tokens by typeTokens$ per 1MCost
Input (uncached)23,144$4.00$0.0926
Cache write0$5.00$0
Cache read0$0.20$0
Output62,676$20.00$1.2535
of which reasoning26,576billed as output
Total computed from tokens
$1.3461
Total reported by the harness
none
Per callTimeTokensCost
call 1: one-shot5m 06s1,245 in, 33,848 out$0.6819
call 2: fix turn3m 53s21,899 in, 28,828 out$0.6642

Two raw API calls, token counts from each response's usage block x list price, summed. Call 2's input includes the first reply and the frame sheet. No harness, so no reported total.

Prices: Project price table (vendor list prices), 2026-09-22.

Run notes

raw call + 1 fix turn (two calls, no tools, no self-review)1 fix turnhuman feedback

  • The fix-turn message and the four-frame sheet the model saw are included in the transcript and as an extra file.
The four frames of the first build that the model was shown in the fix turn
The four frames of the first build that the model was shown in the fix turn